Generate Architecture Decision Records that capture the reasoning behind technical decisions. Use when the user asks to "create an ADR", "document a decision", "record why we chose X", or discusses architectural trade-offs worth preserving.
90
Quality
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Generate an Architecture Decision Record (ADR) based on the conversation context and any architectural decisions discussed.
Create a markdown file with this structure:
# ADR-[NUMBER]: [TITLE]
**Date:** [YYYY-MM-DD]
**Status:** [Proposed | Accepted | Deprecated | Superseded]
**Deciders:** [Who was involved]
## Context
What is the issue that we're seeing that is motivating this decision or change?
## Decision
What is the change that we're proposing and/or doing?
## Consequences
What becomes easier or more difficult to do because of this change?
### Positive
- [Benefit 1]
- [Benefit 2]
### Negative
- [Trade-off 1]
- [Trade-off 2]
### Risks
- [Risk and mitigation]
## Alternatives Considered
### [Alternative 1]
- **Description:** What was this option?
- **Rejected because:** Why didn't we choose it?
### [Alternative 2]
- **Description:** What was this option?
- **Rejected because:** Why didn't we choose it?
## References
- [Related PR, issue, or document]
- [Relevant discussion or prior art]Extract from context — Use the conversation to identify:
Find the ADR location — Look for existing ADRs:
docs/adr/ or docs/decisions/adr/ at project rootdocs/adr/Number appropriately — Check existing ADRs and use the next number
Write concisely — ADRs should be scannable:
Capture the why — The decision itself ages; the reasoning stays valuable
/research — Research informs the decision; ADR captures it/review — Reviews that surface architectural decisions belong in ADRsskills/FRAMEWORKS.md — Full framework index96a72fa
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.